Bone age assessment using hand-wrist X-ray images is fundamental when diagnosing growth disorders of a child or providing a more patient-specific treatment. However, as clinical procedures are a subjective assessment, the accuracy depends highly on the doctor’s experience. Motivated by this, a deep learning-based computer-aided diagnosis method was proposed for performing bone age assessment. Inspired by clinical approaches and aimed to reduce expensive manual annotations, informative regions localization based on a complete unsupervised learning method was firstly performed and an image-processing pipeline was proposed. Subsequently, an image model with pre-trained weights as a backbone was utilized to enhance the reliability of prediction. The prediction head was implemented by a Multiple Layer Perceptron with one hidden layer. In compliance with clinical studies, gender information was an additional input to the prediction head by embedded into the feature vector calculated from the backbone model. After the experimental comparison study, the best results showed a mean absolute error of 6.2 months on the public RSNA dataset and 5.1 months on the additional dataset using MobileNetV3 as the backbone.

The polymerase chain reaction (PCR) is essential in nucleic acid amplification tests and is widely used in many applications such as infectious disease detection, tumor screening, and food safety testing; however, most PCR devices have inefficient heating and cooling ramp rates for the solution, which significantly limit their application in special scenarios such as hospital emergencies, airports, and customs. Here, we propose a temperature control strategy to significantly increase the ramp rates for the solution temperature by switching microfluidic chips between multiple temperature zones and excessively increasing the temperature difference between temperature zones and the solution; accordingly, we have designed an ultrafast thermocycler. The results showed that the ramp rates of the solution temperature are a linear function of temperature differences within a range, and a larger temperature difference would result in faster ramp rates. The maximum heating and cooling ramp rates of the 25 μL solution reached 24.12 °C/s and 25.28 °C/s, respectively, and the average ramp rate was 13.33 °C/s, 6–8 times higher than that of conventional commercial PCR devices. The thermocycler achieved 9 min (1 min pre-denaturation + 45 PCR cycles) ultrafast nucleic acid amplification, shortening the time by 92% compared to the conventional 120 min nucleic acid amplification, and has the potential to be used for rapid nucleic acid detection.

Recently, single-particle cryo-electron microscopy (cryo-EM) has become an indispensable method for determining macromolecular structures at high resolution to deeply explore the relevant molecular mechanism. Its recent breakthrough is mainly because of the rapid advances in hardware and image processing algorithms, especially machine learning. As an essential support of single-particle cryo-EM, machine learning has powered many aspects of structure determination and greatly promoted its development. In this article, we provide a systematic review of the applications of machine learning in this field. Our review begins with a brief introduction of single-particle cryo-EM, followed by the specific tasks and challenges of its image processing. Then, focusing on the workflow of structure determination, we describe relevant machine learning algorithms and applications at different steps, including particle picking, 2-D clustering, 3-D reconstruction, and other steps. As different tasks exhibit distinct characteristics, we introduce the evaluation metrics for each task and summarize their dynamics of technology development. Finally, we discuss the open issues and potential trends in this promising field.

The shortcomings of standard plasma-separation methods limit the point-of-care application of microfluidics in clinical facilities and at the patient’s bedside. To overcome the limitations of this inconvenient, laborious, and costly technique, a new plasma-separation technique and device were developed. This new separation method relies on immunological capture and filtration to exclude cells from plasma, and is convenient, easy to use, and cost-effective. Most of the RBCs can be captured and immobilized by antibody which coated in separation matrix, and residue cells can be totally removed from the sample by a commercially plasma purification membranes. A 400 µL anti-coagulated whole blood sample with 65% hematocrit (Hct) can be separated by the device in 5 min with only one pipette. Up to 97% of the plasma can be recovered from the raw blood sample with a separation efficiency at 100%. The recovery rate of small molecule compounds, proteins, and nucleic acid biomarkers is evaluated; there are no obvious differences from the centrifuge method. The results demonstrate that this method is an excellent replacement for traditional plasma preparation protocols.

Cryo-electron microscopy (cryo-EM) is a widely used structural determination technique. Because of the extremely low signal-to-noise ratio (SNR) of images captured by cryo-EM, clustering single-particle cryo-EM images with high accuracy is challenging. To address this, we proposed an iterative denoising and clustering method based on a deep convolutional variational autoencoder and K-means++. The proposed method contains two modules: a denoising ResNet variational autoencoder (DRVAE), and Balance size K-means++ (BSK-means++). First, the DRVAE is trained in a fully unsupervised manner to initialize the neural network and obtain preliminary denoised images. Second, BSK-means++ is built for clustering denoised images, and images closer to class centers are divided into reliable samples. Third, the training of DRVAE is continued, while the class-average images are used as pseudo supervision of reliable samples to reserve more detailed information of denoised images. Finally, the second and third steps mentioned above can be performed jointly and iteratively until convergence occurs. The experimental results showed that the proposed method can generate reliable class average images and achieve better clustering accuracy and normalized mutual information than current methods. This study confirmed that DRVAE with BSK-means++ could achieve a good denoise performance on single-particle cryo-EM images, which can help researchers obtain information such as symmetry and heterogeneity of the target particles. In addition, the proposed method avoids the extreme imbalance of class size, which improves the reliability of the clustering result.